switch back to flash and add sleep

app.py

@@ -5,6 +5,7 @@ import inspect
 import pandas as pd
 import asyncio
 import sys
+import time
 from llama_index.llms.google_genai import GoogleGenAI
 from llama_index.tools.duckduckgo import DuckDuckGoSearchToolSpec
 from llama_index.core.agent.workflow import AgentWorkflow
@@ -27,7 +28,7 @@ class BasicAgent:
             raise ValueError("GEMINI_API_KEY not set in environment variables.")
 
         self.model = GoogleGenAI(
-            model="gemini-2.0-flash-lite",
+            model="gemini-2.0-flash",
             api_key=gemini_api_key
         )
 
@@ -121,6 +122,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
     for item in questions_data:
+        time.sleep(5) # To avoid rate limiting issues, you can adjust this delay as needed
         task_id = item.get("task_id")
         question_text = item.get("question")
         file_name = item.get("file_name")